Diabetic retinopathy is a common condition of an ailment where the retina is harmed on the grounds that fluid breaks away from the walls of blood vessels into the retina. The large population is affected by diabetic retinopathy and hence research in the area of automated screening has acquired major research interest in the scientific community. The diagnosing features for diabetic retinopathy comprises of identifying deformations of minute blood vessel in form of exudates and its features occurring in and around the regions of fundus which will result into exudes, hemorrhages, or microaneurysms. This feature is often hard to be classified by naked eyes and need trained personnel for close inspection before making diagnosis. Therefore, a comprehensive machine learning tool is in the demand for automated diabetic retinopathy detection. Neural networks have given promising results in the field of classification. Therefore, we present a hybrid neural network-based method with realistic clinical potential. In this study, we present a neuro-fuzzy technique, which is developed for identification of exudates in retinal images and is utilized for the extraction of essential features from the retinal images of patient’s eyeballs. We trained this hybrid neural network base technique over a set of 25,600 training images for color retinal images and tested it over 12,000 testing image set for binocular model. The method achieves an accuracy of 95.4% recognition on non-noisy images and 93% on noisy images; thereby giving a consistency rate of 91% in correspondence with the ophthalmologist.
Development of an Automated Screening System for Retinopathy of Prematurity Using a Deep Neural Network for Wide-Angle Retinal Images
